runninghub-image
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RUNNINGHUB_API_KEY | Yes | RunningHub API Key created on the RunningHub API management page (在 RunningHub API 管理页面点「新建」创建) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| runninghub_search_modelsB | 搜索 RunningHub 模型目录（350+ 标准模型 API 端点）。按关键词/类别/分组查找模型，返回可用的 endpoint 与说明。类别：image=图像、video=视频、audio=音频、other=其他（3D 等）。找到模型后用 runninghub_submit_task 提交任务。 |
| runninghub_list_modelsC | 按类别浏览 RunningHub 模型目录。category=image|video|audio|other。 |
| runninghub_submit_taskA | 提交 RunningHub 标准模型任务。先用 runninghub_search_models 找到目标模型的 endpoint，再把该模型文档要求的参数放进 params。返回 taskId，可用 runninghub_wait_task 等待结果。注意：标准模型 API 需要企业级-共享 API Key。 |
| runninghub_query_taskA | 查询 RunningHub 任务状态与结果（单次查询）。v2 用于标准模型任务；legacy 用于工作流/AI 应用任务。 |
| runninghub_wait_taskA | 轮询等待 RunningHub 任务完成（每 5 秒查询一次，直到 SUCCESS / FAILED 或超时）。返回结果文件 URL 列表。 |
| runninghub_upload_fileA | 上传本地文件（图片/视频/音频/压缩包）到 RunningHub，返回 fileName。工作流/AI 应用的图片、音频、视频节点参数请把该 fileName 填入 fieldValue。 |
| runninghub_download_fileC | 把任务结果文件（URL）下载到本地指定路径。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Most tools have clearly distinct purposes: submit/query/wait tasks, upload/download files. However, search_models and list_models both retrieve the model catalog, and an agent may need to read descriptions carefully to choose between keyword search and category browsing. The overlap is minor but present.
All tool names follow the same predictable pattern: runninghub_ prefix plus verb_noun (search_models, list_models, submit_task, query_task, wait_task, upload_file, download_file). The snake_case convention is consistent throughout with no deviations.
Seven tools is a well-scoped set for an image generation service. Each tool covers a necessary step in the workflow: discovery, submission, monitoring, and file transfer. No tool feels redundant or excessive.
The surface covers the core lifecycle: finding models, submitting tasks, polling for results, and uploading/downloading files. Minor gaps exist, such as no explicit task cancellation and no tool to submit workflow/AI-app tasks despite query_task mentioning legacy support for them.